© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    words related to biological experiments and scientific research involving animals

    oai_token-act-pair · gemini-2.0-flash

    Animals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.63
     cars
    -0.60
    HtmlAttribute
    -0.59
     Horses
    -0.56
     vehicles
    -0.56
     Vehicles
    -0.55
     guns
    -0.55
     horses
    -0.54
    RunAsync
    -0.54
    vehicles
    -0.54
    POSITIVE LOGITS
     animal
    1.15
    animal
    0.90
     cat
    0.85
    Animal
    0.84
     mouse
    0.84
     Animal
    0.82
     ANIMAL
    0.82
     plant
    0.81
     rat
    0.78
     bird
    0.78
    Activations Density 11.193%

    No Known Activations